Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MathAndMagic/bridgeapp-plugin --skill bridgeapp-specgit clone --depth 1 https://github.com/MathAndMagic/bridgeapp-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-spec)<a href="https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-spec"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-spec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-spec"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.00393 |
| Opus 5.5 | $0.00027 | $0.00157 |
| Sonnet 5.5 | $0.00013 | $0.00079 |
| Haiku 4.5 | $0.00007 | $0.00039 |
Grade A, and why
bridgeapp-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Writing a spec
A spec describes how something works, so that whoever does the work can do it without asking back, and whoever approves it can approve it without digging. Nothing else goes in.
Context first
Find out what was already decided before asking anything: the task, its
threads, older discussions nobody linked, existing documents, and any other
source you can reach — not only BridgeApp. Gathering the decision history is
what bridgeapp-investigation does; use it.
If a document on the same subject already exists, ask the author whether to update it or write a new one.
Ask
- Contradictions between sources, or between the request and an earlier decision: show both sides with their sources and let the author choose.
- Additions the context holds and the author did not mention: offer them, add only what they accept.
- Gaps that matter for doing the work: ask.
An open question goes into the document only if the author agrees to it.
Write
- How it works, stated concretely enough to check. No instructions on how to build it, no filler.
- References next to the point they illustrate — screenshots, media, links to the source. One link at the top is not enough.
- Every statement comes from a source or from the author.
Every time
After writing or changing the document, ask the author to read it carefully before it goes to the task or to anyone else.
Reply in the user's language.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 46 lines · 67 tokens per session scan A 31dd558f7b16
bridgeapp-spec is a skill published in the GitHub repository MathAndMagic/bridgeapp-plugin (0 stars, last pushed 11d ago), licensed MIT. It adds 67 tokens to every session and 393 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
bridgeapp-spec compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bridgeapp-specMathAndMagic/bridgeapp-plugin | Skill | 0 | 11d ago | MIT | A | 67 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |